TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Series

• URL: http://arxiv.org/abs/2602.22520v1
• Date: Thu, 26 Feb 2026 01:31:58 GMT
• Title: TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Series
• Authors: Xiannan Huang, Shen Fang, Shuhan Qiu, Chengcheng Yu, Jiayuan Du, Chao Yang,
• Abstract summary: We propose a unified learning framework that explicitly incorporates historical residuals into the forecasting pipeline during both training and evaluation.<n>Experiments across 10 real-world datasets and 5 backbone architectures show that TEFL consistently improves accuracy, reducing MAE by 5-10% on average.<n>It demonstrates strong robustness under abrupt changes and distribution shifts, with error reductions exceeding 10% (up to 19.5%) in challenging scenarios.
• Score: 4.942021101617155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series forecasting plays a critical role in domains such as transportation, energy, and meteorology. Despite their success, modern deep forecasting models are typically trained to minimize point-wise prediction loss without leveraging the rich information contained in past prediction residuals from rolling forecasts - residuals that reflect persistent biases, unmodeled patterns, or evolving dynamics. We propose TEFL (Temporal Error Feedback Learning), a unified learning framework that explicitly incorporates these historical residuals into the forecasting pipeline during both training and evaluation. To make this practical in deep multi-step settings, we address three key challenges: (1) selecting observable multi-step residuals under the partial observability of rolling forecasts, (2) integrating them through a lightweight low-rank adapter to preserve efficiency and prevent overfitting, and (3) designing a two-stage training procedure that jointly optimizes the base forecaster and error module. Extensive experiments across 10 real-world datasets and 5 backbone architectures show that TEFL consistently improves accuracy, reducing MAE by 5-10% on average. Moreover, it demonstrates strong robustness under abrupt changes and distribution shifts, with error reductions exceeding 10% (up to 19.5%) in challenging scenarios. By embedding residual-based feedback directly into the learning process, TEFL offers a simple, general, and effective enhancement to modern deep forecasting systems.

Related papers

• EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting [34.793750131438934]
  Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness.<n>We present a novel pipeline across pretraining, finetuning and forecasting to enhance long-context modeling while reducing computational overhead.<n>We introduce an Efficient Multi-scale Transformer (EMFormer) to extract multi-scale features through a single convolution in both training and inference.
  arXiv  Detail & Related papers  (2026-02-01T12:36:01Z)
• The Forecast Critic: Leveraging Large Language Models for Poor Forecast Identification [74.64864354503204]
  We propose The Forecast Critic, a system that leverages Large Language Models (LLMs) for automated forecast monitoring.<n>We evaluate the ability of LLMs to assess time series forecast quality.<n>We present three experiments, including on both synthetic and real-world forecasting data.
  arXiv  Detail & Related papers  (2025-12-12T21:59:53Z)
• A Diffusion-Based Framework for High-Resolution Precipitation Forecasting over CONUS [0.410492188035848]
  This study introduces a diffusion-based deep learning (DL) framework that systematically compares three residual prediction strategies differing only in their input sources.<n>Forecasts are produced at 1-km spatial resolution, beginning with direct 1-hour predictions and extending to 12 hours using autoregressive rollouts.
  arXiv  Detail & Related papers  (2025-12-09T19:23:27Z)
• Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model [20.98899316909536]
  We introduce Baguan, a novel data-driven model for medium-range weather forecasting built on a Siamese Autoencoder pre-trained in a self-supervised manner.<n> Experimental results show that Baguan outperforms traditional methods, delivering more accurate forecasts.
  arXiv  Detail & Related papers  (2025-05-20T03:29:23Z)
• IISE PG&E Energy Analytics Challenge 2025: Hourly-Binned Regression Models Beat Transformers in Load Forecasting [0.0]
  This study evaluates forecasting models ranging from classical regression techniques to advanced deep learning architectures.<n>The dataset includes two years of historical electricity load data, alongside temperature and global horizontal irradiance (GHI) across five sites.<n>Our results reveal that deep learning models, including TimeGPT, fail to consistently outperform simpler statistical and machine learning approaches.
  arXiv  Detail & Related papers  (2025-05-16T15:55:34Z)
• Directly Forecasting Belief for Reinforcement Learning with Delays [41.52768902667611]
  Reinforcement learning with delays is challenging as sensory perceptions lag behind the actual events.<n>We develop a novel belief estimation method named Directly Forecasting Belief Transformer (DFBT)<n>DFBT directly forecasts states from observations without incrementally estimating intermediate states step-by-step.
  arXiv  Detail & Related papers  (2025-05-01T14:20:48Z)
• Overtrained Language Models Are Harder to Fine-Tune [64.44743256512237]
  Large language models are pre-trained on ever-growing token budgets.<n>We show that extended pre-training can make models harder to fine-tune, leading to degraded final performance.
  arXiv  Detail & Related papers  (2025-03-24T23:11:56Z)
• Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models [68.23649978697027]
  Forecast-PEFT is a fine-tuning strategy that freezes the majority of the model's parameters, focusing adjustments on newly introduced prompts and adapters. Our experiments show that Forecast-PEFT outperforms traditional full fine-tuning methods in motion prediction tasks. Forecast-FT further improves prediction performance, evidencing up to a 9.6% enhancement over conventional baseline methods.
  arXiv  Detail & Related papers  (2024-07-28T19:18:59Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.